arXiv AI
When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 10
TrojanWorld: Backdooring World-Model Agents via Imagination Steering
TrojanWorld is a backdoor framework that targets world-model agents by steering their internal imagination toward attacker-specified actions when a physical trigger is present. The attack uses Decision-Reflective Induction, Clean Behavior Anchoring, and Causal Propagation to maintain stealth, persistence, and high performance. Experiments on TD-MPC2, DreamerV3, and R2-Dreamer across several benchmarks show that the attack can induce target actions with minimal performance loss and can keep agents on a malicious trajectory even after the trigger is removed.
arXiv Machine Learning
Jul 30
ToxScreen: Detecting Whether an LLM Has Been Poisoned
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
arXiv Machine Learning
Jun 18
Stealthy World Model Manipulation via Data Poisoning
arXiv:2606. 18697v1 Announce Type: new Abstract: Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments.
arXiv AI
Aug 13
Backdoor Decontamination Dynamics in LLM Agents
arXiv:2608. 11295v1 Announce Type: cross Abstract: Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing.
Hugging Face Trending Papers
Jul 29
ToxScreen: Detecting Whether an LLM Has Been Poisoned
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv Computation and Language
Aug 25
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...